xapian-fu 1.7.0 → 1.8.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (92) hide show
  1. checksums.yaml +4 -4
  2. data/README.rdoc +2 -1
  3. data/lib/xapian_fu/stopper_factory.rb +1 -4
  4. data/lib/xapian_fu/stopwords/af.txt +51 -0
  5. data/lib/xapian_fu/stopwords/ar.txt +480 -0
  6. data/lib/xapian_fu/stopwords/bg.txt +259 -0
  7. data/lib/xapian_fu/stopwords/bn.txt +398 -0
  8. data/lib/xapian_fu/stopwords/br.txt +1203 -0
  9. data/lib/xapian_fu/stopwords/ca.txt +278 -0
  10. data/lib/xapian_fu/stopwords/cs.txt +423 -0
  11. data/lib/xapian_fu/stopwords/da.txt +170 -0
  12. data/lib/xapian_fu/stopwords/danish.txt +1 -0
  13. data/lib/xapian_fu/stopwords/de.txt +620 -0
  14. data/lib/xapian_fu/stopwords/dutch.txt +1 -0
  15. data/lib/xapian_fu/stopwords/el.txt +847 -0
  16. data/lib/xapian_fu/stopwords/en.txt +1298 -0
  17. data/lib/xapian_fu/stopwords/english.txt +1 -0
  18. data/lib/xapian_fu/stopwords/eo.txt +173 -0
  19. data/lib/xapian_fu/stopwords/es.txt +732 -0
  20. data/lib/xapian_fu/stopwords/et.txt +35 -0
  21. data/lib/xapian_fu/stopwords/eu.txt +98 -0
  22. data/lib/xapian_fu/stopwords/fa.txt +799 -0
  23. data/lib/xapian_fu/stopwords/fi.txt +847 -0
  24. data/lib/xapian_fu/stopwords/finnish.txt +1 -0
  25. data/lib/xapian_fu/stopwords/fr.txt +691 -0
  26. data/lib/xapian_fu/stopwords/french.txt +1 -0
  27. data/lib/xapian_fu/stopwords/ga.txt +109 -0
  28. data/lib/xapian_fu/stopwords/german.txt +1 -0
  29. data/lib/xapian_fu/stopwords/gl.txt +160 -0
  30. data/lib/xapian_fu/stopwords/gu.txt +224 -0
  31. data/lib/xapian_fu/stopwords/ha.txt +39 -0
  32. data/lib/xapian_fu/stopwords/he.txt +194 -0
  33. data/lib/xapian_fu/stopwords/hi.txt +225 -0
  34. data/lib/xapian_fu/stopwords/hr.txt +179 -0
  35. data/lib/xapian_fu/stopwords/hu.txt +789 -0
  36. data/lib/xapian_fu/stopwords/hungarian.txt +1 -0
  37. data/lib/xapian_fu/stopwords/hy.txt +45 -0
  38. data/lib/xapian_fu/stopwords/id.txt +758 -0
  39. data/lib/xapian_fu/stopwords/it.txt +632 -0
  40. data/lib/xapian_fu/stopwords/italian.txt +1 -0
  41. data/lib/xapian_fu/stopwords/ja.txt +134 -0
  42. data/lib/xapian_fu/stopwords/ko.txt +679 -0
  43. data/lib/xapian_fu/stopwords/ku.txt +62 -0
  44. data/lib/xapian_fu/stopwords/la.txt +49 -0
  45. data/lib/xapian_fu/stopwords/lt.txt +474 -0
  46. data/lib/xapian_fu/stopwords/lv.txt +161 -0
  47. data/lib/xapian_fu/stopwords/mr.txt +99 -0
  48. data/lib/xapian_fu/stopwords/ms.txt +475 -0
  49. data/lib/xapian_fu/stopwords/nl.txt +413 -0
  50. data/lib/xapian_fu/stopwords/no.txt +221 -0
  51. data/lib/xapian_fu/stopwords/norwegian.txt +1 -0
  52. data/lib/xapian_fu/stopwords/pl.txt +329 -0
  53. data/lib/xapian_fu/stopwords/portuguese.txt +1 -0
  54. data/lib/xapian_fu/stopwords/pt.txt +560 -0
  55. data/lib/xapian_fu/stopwords/ro.txt +434 -0
  56. data/lib/xapian_fu/stopwords/ru.txt +559 -0
  57. data/lib/xapian_fu/stopwords/russian.txt +1 -0
  58. data/lib/xapian_fu/stopwords/sk.txt +418 -0
  59. data/lib/xapian_fu/stopwords/sl.txt +446 -0
  60. data/lib/xapian_fu/stopwords/so.txt +30 -0
  61. data/lib/xapian_fu/stopwords/spanish.txt +1 -0
  62. data/lib/xapian_fu/stopwords/st.txt +31 -0
  63. data/lib/xapian_fu/stopwords/sv.txt +418 -0
  64. data/lib/xapian_fu/stopwords/sw.txt +74 -0
  65. data/lib/xapian_fu/stopwords/swedish.txt +1 -0
  66. data/lib/xapian_fu/stopwords/th.txt +116 -0
  67. data/lib/xapian_fu/stopwords/tl.txt +147 -0
  68. data/lib/xapian_fu/stopwords/tr.txt +504 -0
  69. data/lib/xapian_fu/stopwords/uk.txt +73 -0
  70. data/lib/xapian_fu/stopwords/update.rb +10 -3
  71. data/lib/xapian_fu/stopwords/ur.txt +517 -0
  72. data/lib/xapian_fu/stopwords/vi.txt +645 -0
  73. data/lib/xapian_fu/stopwords/yo.txt +60 -0
  74. data/lib/xapian_fu/stopwords/zh.txt +794 -0
  75. data/lib/xapian_fu/stopwords/zu.txt +29 -0
  76. data/lib/xapian_fu/version.rb +1 -1
  77. data/lib/xapian_fu/xapian_db.rb +3 -0
  78. data/spec/xapian_doc_spec.rb +1 -1
  79. metadata +109 -51
  80. data/lib/xapian_fu/stopwords/danish.txt +0 -102
  81. data/lib/xapian_fu/stopwords/dutch.txt +0 -113
  82. data/lib/xapian_fu/stopwords/english.txt +0 -312
  83. data/lib/xapian_fu/stopwords/finnish.txt +0 -89
  84. data/lib/xapian_fu/stopwords/french.txt +0 -168
  85. data/lib/xapian_fu/stopwords/german.txt +0 -286
  86. data/lib/xapian_fu/stopwords/hungarian.txt +0 -203
  87. data/lib/xapian_fu/stopwords/italian.txt +0 -295
  88. data/lib/xapian_fu/stopwords/norwegian.txt +0 -186
  89. data/lib/xapian_fu/stopwords/portuguese.txt +0 -245
  90. data/lib/xapian_fu/stopwords/russian.txt +0 -236
  91. data/lib/xapian_fu/stopwords/spanish.txt +0 -348
  92. data/lib/xapian_fu/stopwords/swedish.txt +0 -125
@@ -0,0 +1,446 @@
1
+ a
2
+ ali
3
+ april
4
+ avgust
5
+ b
6
+ bi
7
+ bil
8
+ bila
9
+ bile
10
+ bili
11
+ bilo
12
+ biti
13
+ blizu
14
+ bo
15
+ bodo
16
+ bojo
17
+ bolj
18
+ bom
19
+ bomo
20
+ boste
21
+ bova
22
+ boš
23
+ brez
24
+ c
25
+ cel
26
+ cela
27
+ celi
28
+ celo
29
+ d
30
+ da
31
+ daleč
32
+ dan
33
+ danes
34
+ datum
35
+ december
36
+ deset
37
+ deseta
38
+ deseti
39
+ deseto
40
+ devet
41
+ deveta
42
+ deveti
43
+ deveto
44
+ do
45
+ dober
46
+ dobra
47
+ dobri
48
+ dobro
49
+ dokler
50
+ dol
51
+ dolg
52
+ dolga
53
+ dolgi
54
+ dovolj
55
+ drug
56
+ druga
57
+ drugi
58
+ drugo
59
+ dva
60
+ dve
61
+ e
62
+ eden
63
+ en
64
+ ena
65
+ ene
66
+ eni
67
+ enkrat
68
+ eno
69
+ etc.
70
+ f
71
+ februar
72
+ g
73
+ g.
74
+ ga
75
+ ga.
76
+ gor
77
+ gospa
78
+ gospod
79
+ h
80
+ halo
81
+ i
82
+ idr.
83
+ ii
84
+ iii
85
+ in
86
+ iv
87
+ ix
88
+ iz
89
+ j
90
+ januar
91
+ jaz
92
+ je
93
+ ji
94
+ jih
95
+ jim
96
+ jo
97
+ julij
98
+ junij
99
+ jutri
100
+ k
101
+ kadarkoli
102
+ kaj
103
+ kajti
104
+ kako
105
+ kakor
106
+ kamor
107
+ kamorkoli
108
+ kar
109
+ karkoli
110
+ katerikoli
111
+ kdaj
112
+ kdo
113
+ kdorkoli
114
+ ker
115
+ ki
116
+ kje
117
+ kjer
118
+ kjerkoli
119
+ ko
120
+ koder
121
+ koderkoli
122
+ koga
123
+ komu
124
+ kot
125
+ kratek
126
+ kratka
127
+ kratke
128
+ kratki
129
+ l
130
+ lahka
131
+ lahke
132
+ lahki
133
+ lahko
134
+ le
135
+ lep
136
+ lepa
137
+ lepe
138
+ lepi
139
+ lepo
140
+ leto
141
+ m
142
+ maj
143
+ majhen
144
+ majhna
145
+ majhni
146
+ malce
147
+ malo
148
+ manj
149
+ marec
150
+ me
151
+ med
152
+ medtem
153
+ mene
154
+ mesec
155
+ mi
156
+ midva
157
+ midve
158
+ mnogo
159
+ moj
160
+ moja
161
+ moje
162
+ mora
163
+ morajo
164
+ moram
165
+ moramo
166
+ morate
167
+ moraš
168
+ morem
169
+ mu
170
+ n
171
+ na
172
+ nad
173
+ naj
174
+ najina
175
+ najino
176
+ najmanj
177
+ naju
178
+ največ
179
+ nam
180
+ narobe
181
+ nas
182
+ nato
183
+ nazaj
184
+ naš
185
+ naša
186
+ naše
187
+ ne
188
+ nedavno
189
+ nedelja
190
+ nek
191
+ neka
192
+ nekaj
193
+ nekatere
194
+ nekateri
195
+ nekatero
196
+ nekdo
197
+ neke
198
+ nekega
199
+ neki
200
+ nekje
201
+ neko
202
+ nekoga
203
+ nekoč
204
+ ni
205
+ nikamor
206
+ nikdar
207
+ nikjer
208
+ nikoli
209
+ nič
210
+ nje
211
+ njega
212
+ njegov
213
+ njegova
214
+ njegovo
215
+ njej
216
+ njemu
217
+ njen
218
+ njena
219
+ njeno
220
+ nji
221
+ njih
222
+ njihov
223
+ njihova
224
+ njihovo
225
+ njiju
226
+ njim
227
+ njo
228
+ njun
229
+ njuna
230
+ njuno
231
+ no
232
+ nocoj
233
+ november
234
+ npr.
235
+ o
236
+ ob
237
+ oba
238
+ obe
239
+ oboje
240
+ od
241
+ odprt
242
+ odprta
243
+ odprti
244
+ okoli
245
+ oktober
246
+ on
247
+ onadva
248
+ one
249
+ oni
250
+ onidve
251
+ osem
252
+ osma
253
+ osmi
254
+ osmo
255
+ oz.
256
+ p
257
+ pa
258
+ pet
259
+ peta
260
+ petek
261
+ peti
262
+ peto
263
+ po
264
+ pod
265
+ pogosto
266
+ poleg
267
+ poln
268
+ polna
269
+ polni
270
+ polno
271
+ ponavadi
272
+ ponedeljek
273
+ ponovno
274
+ potem
275
+ povsod
276
+ pozdravljen
277
+ pozdravljeni
278
+ prav
279
+ prava
280
+ prave
281
+ pravi
282
+ pravo
283
+ prazen
284
+ prazna
285
+ prazno
286
+ prbl.
287
+ precej
288
+ pred
289
+ prej
290
+ preko
291
+ pri
292
+ pribl.
293
+ približno
294
+ primer
295
+ pripravljen
296
+ pripravljena
297
+ pripravljeni
298
+ proti
299
+ prva
300
+ prvi
301
+ prvo
302
+ r
303
+ ravno
304
+ redko
305
+ res
306
+ reč
307
+ s
308
+ saj
309
+ sam
310
+ sama
311
+ same
312
+ sami
313
+ samo
314
+ se
315
+ sebe
316
+ sebi
317
+ sedaj
318
+ sedem
319
+ sedma
320
+ sedmi
321
+ sedmo
322
+ sem
323
+ september
324
+ seveda
325
+ si
326
+ sicer
327
+ skoraj
328
+ skozi
329
+ slab
330
+ smo
331
+ so
332
+ sobota
333
+ spet
334
+ sreda
335
+ srednja
336
+ srednji
337
+ sta
338
+ ste
339
+ stran
340
+ stvar
341
+ sva
342
+ t
343
+ ta
344
+ tak
345
+ taka
346
+ take
347
+ taki
348
+ tako
349
+ takoj
350
+ tam
351
+ te
352
+ tebe
353
+ tebi
354
+ tega
355
+ težak
356
+ težka
357
+ težki
358
+ težko
359
+ ti
360
+ tista
361
+ tiste
362
+ tisti
363
+ tisto
364
+ tj.
365
+ tja
366
+ to
367
+ toda
368
+ torek
369
+ tretja
370
+ tretje
371
+ tretji
372
+ tri
373
+ tu
374
+ tudi
375
+ tukaj
376
+ tvoj
377
+ tvoja
378
+ tvoje
379
+ u
380
+ v
381
+ vaju
382
+ vam
383
+ vas
384
+ vaš
385
+ vaša
386
+ vaše
387
+ ve
388
+ vedno
389
+ velik
390
+ velika
391
+ veliki
392
+ veliko
393
+ vendar
394
+ ves
395
+ več
396
+ vi
397
+ vidva
398
+ vii
399
+ viii
400
+ visok
401
+ visoka
402
+ visoke
403
+ visoki
404
+ vsa
405
+ vsaj
406
+ vsak
407
+ vsaka
408
+ vsakdo
409
+ vsake
410
+ vsaki
411
+ vsakomur
412
+ vse
413
+ vsega
414
+ vsi
415
+ vso
416
+ včasih
417
+ včeraj
418
+ x
419
+ z
420
+ za
421
+ zadaj
422
+ zadnji
423
+ zakaj
424
+ zaprta
425
+ zaprti
426
+ zaprto
427
+ zdaj
428
+ zelo
429
+ zunaj
430
+ č
431
+ če
432
+ često
433
+ četrta
434
+ četrtek
435
+ četrti
436
+ četrto
437
+ čez
438
+ čigav
439
+ š
440
+ šest
441
+ šesta
442
+ šesti
443
+ šesto
444
+ štiri
445
+ ž
446
+ že
@@ -0,0 +1,30 @@
1
+ aad
2
+ albaabkii
3
+ atabo
4
+ ay
5
+ ayaa
6
+ ayee
7
+ ayuu
8
+ dhan
9
+ hadana
10
+ in
11
+ inuu
12
+ isku
13
+ jiray
14
+ jirtay
15
+ ka
16
+ kale
17
+ kasoo
18
+ ku
19
+ kuu
20
+ lakin
21
+ markii
22
+ oo
23
+ si
24
+ soo
25
+ uga
26
+ ugu
27
+ uu
28
+ waa
29
+ waxa
30
+ waxuu
@@ -0,0 +1 @@
1
+ es.txt
@@ -0,0 +1,31 @@
1
+ a
2
+ ba
3
+ bane
4
+ bona
5
+ e
6
+ ea
7
+ eaba
8
+ empa
9
+ ena
10
+ ha
11
+ hae
12
+ hape
13
+ ho
14
+ hore
15
+ ka
16
+ ke
17
+ la
18
+ le
19
+ li
20
+ me
21
+ mo
22
+ moo
23
+ ne
24
+ o
25
+ oa
26
+ re
27
+ sa
28
+ se
29
+ tloha
30
+ tsa
31
+ tse